← Back to community benchmarks

gemma-4-31b-it-oQ6e

M5 Max (40c) · 128 GB · 6bit · 2026-07-19
Performance
1k
tokens
713.5
PP tok/s
18.1
TG tok/s
1435
TTFT (ms)
25.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.5.2.dev1
macOS macOS 27.0
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 713.5 18.1 25.3 GB current
4k 655.2 17.5 27.3 GB view
32k 546.9 14.4 51.3 GB view
64k 415.8 11.0 78.9 GB view
Batching Results
Batch Size TG tok/s Speedup
18.1 1.00×
33.5 1.85×
54.9 3.03×